Face Recognition from Facial Surface Metric

  • Alexander M. Bronstein
  • Michael M. Bronstein
  • Alon Spira
  • Ron Kimmel
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3022)


Recently, a 3D face recognition approach based on geometric invariant signatures, has been proposed. The key idea is a representation of the facial surface, invariant to isometric deformations, such as those resulting from facial expressions. One important stage in the construction of the geometric invariants involves in measuring geodesic distances on triangulated surfaces, which is carried out by the fast marching on triangulated domains algorithm.

Proposed here is a method that uses only the metric tensor of the surface for geodesic distance computation. That is, the explicit integration of the surface in 3D from its gradients is not needed for the recognition task. It enables the use of simple and cost-efficient 3D acquisition techniques such as photometric stereo. Avoiding the explicit surface reconstruction stage saves computational time and reduces numerical errors.


Face Recognition Geodesic Distance Facial Surface Surface Gradient Photometric Stereo 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Gordon, G.: Face recognition from frontal and profile views. In: Proc. Int’l Workshop on Face and Gesture Recognition, pp. 47–52 (1997)Google Scholar
  2. 2.
    Beumier, C., Acheroy, M.P.: Automatic face authentication from 3D surface. In: Proc. British Machine Vision Conf., pp. 449–458 (1988)Google Scholar
  3. 3.
    Huang, J., Blanz, V., Heisele, V.: Face recognition using component-based SVM classification and morphable models. In: SVM, pp. 334–341 (2002)Google Scholar
  4. 4.
    Mavridis, N., Tsalakanidou, F., Pantazis, D., Malassiotis, S., Strintzis, M.G.: The HISCORE face recognition application: Affordable desktop face recognition based on a novel 3D camera. In: Proc. Int’l Conf. Augmented Virtual Environments and 3D Imaging, Mykonos, Greece (2001)Google Scholar
  5. 5.
    Bronstein, A., Bronstein, M., Kimmel, R.: Expression-invariant 3D face recognition. In: Kittler, J., Nixon, M.S. (eds.) AVBPA 2003. LNCS, vol. 2688, pp. 62–69. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  6. 6.
    Elad, A., Kimmel, R.: Bending invariant representations for surfaces. In: Proc. CVPR, pp. 168–174 (2001), pp. 415–438 (1997)Google Scholar
  7. 7.
    Kimmel, R., Sethian, J.A.: Computing geodesic on manifolds. Proc. US National Academy of Science 95, 8431–8435 (1998)zbMATHCrossRefMathSciNetGoogle Scholar
  8. 8.
    Sethian, J.A.: A review of the theory, algorithms, and applications of level set method for propagating surfaces. In: Acta numerica, pp. 309–395 (1996)Google Scholar
  9. 9.
    Bronstein, A., Bronstein, M., Gordon, E., Kimmel, R.: High-resolution structured light range scanner with automatic calibration. Techn. Report CIS-2003-06, Dept. Computer Science, Technion, Israel (2003)Google Scholar
  10. 10.
    Borg, I., Groenen, P.: Modern multidimensional scaling - theory and applications. Springer, Heidelberg (1997)zbMATHGoogle Scholar
  11. 11.
    Proesmans, M., Van Gool, L., Oosterlinck, A.: One-shot active shape acquisition. In: Proc. Internat. Conf. Pattern Recognition, Vienna, vol. C, pp. 336–340 (1996)Google Scholar
  12. 12.
    Winkelbach, S., Wahl, F.M.: Shape from 2D edge gradients. In: Radig, B., Florczyk, S. (eds.) DAGM 2001. LNCS, vol. 2191, pp. 377–384. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  13. 13.
    Winkelbach, S., Wahl, F.M.: Shape from single stripe pattern illumination. In: Van Gool, L. (ed.) DAGM 2002. LNCS, vol. 2449, pp. 240–247. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  14. 14.
    Schwartz, E.L., Shaw, A., Wolfson, E.: A numerical solution to the generalized mapmaker’s problem: flattening nonconvex polyhedral surfaces. IEEE Trans. PAMI 11, 1005–1008 (1989)Google Scholar
  15. 15.
    Faugeras, O.D., Hebert, M.: A 3D recognition and positioning algorithm using geometrical matching between primitive surfaces. In: Proc. 7th Int’l Joint Conf. on Artificial Intelligence, pp. 996–1002 (1983)Google Scholar
  16. 16.
    Besl, P.J.: The free form matching problem. In: Freeman, H. (ed.) Machine vision for three-dimensional scene, Academic, New York (1990)Google Scholar
  17. 17.
    Barequet, G., Sharir, M.: Recovering the position and orientation of free-form objects from image contours using 3D distance map. IEEE Trans. PAMI 19(9), 929–948 (1997)Google Scholar
  18. 18.
    Tal, A., Elad, M., Ar, S.: Content based retrieval of VRML objects - an iterative and interactive approach. EG Multimedia 97, 97–108 (2001)Google Scholar
  19. 19.
    Sethian, J., Vladimirsky, A.: Ordered upwind methods for static Hamilton-Jacobi equations: theory and applications. Techn. Report PAM 792, Center for Pure and Applied Mathematics, Univ. Calif. Berkeley (2001)Google Scholar
  20. 20.
    Memoli, F., Sapiro, G.: Fast computation of weighted distance functions and geodesics on implicit hyper-surfaces. Journal of Computational Physics 173(2), 730–764 (2001)zbMATHCrossRefMathSciNetGoogle Scholar
  21. 21.
  22. 22.
    Spira, A., Kimmel, R.: An efficient solution to the eikonal equation on parametric manifolds. In: INTERPHASE 2003 meeting, Isaac Newton Institute for Mathematical Sciences, 2003 Preprints, Preprint No. NI03045-CPD, UK (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Alexander M. Bronstein
    • 1
  • Michael M. Bronstein
    • 1
  • Alon Spira
    • 2
  • Ron Kimmel
    • 2
  1. 1.Department of Electrical EngineeringTechnion – Israel Institute of TechnologyHaifaIsrael
  2. 2.Department of Computer ScienceTechnion – Israel Institute of TechnologyHaifaIsrael

Personalised recommendations